{"id":"https://openalex.org/W192266936","doi":"https://doi.org/10.21437/interspeech.2004-275","title":"Comparison of ML, MAP, and VB based acoustic models in large vocabulary speech recognition","display_name":"Comparison of ML, MAP, and VB based acoustic models in large vocabulary speech recognition","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W192266936","doi":"https://doi.org/10.21437/interspeech.2004-275","mag":"192266936"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-275","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004058551","display_name":"Panu Somervuo","orcid":"https://orcid.org/0000-0003-3121-4047"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Panu Juhani Somervuo","raw_affiliation_strings":["Helsinki University of Technology"],"affiliations":[{"raw_affiliation_string":"Helsinki University of Technology","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5004058551"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4625,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73295407,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"701","last_page":"704"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9818000197410583,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.8701549768447876},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.8613893985748291},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.713835597038269},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6778420805931091},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.660330057144165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5384151339530945},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5303630828857422},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5127550363540649},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5040079951286316},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48957642912864685},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4861466586589813},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.4825098514556885},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.46457892656326294},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3470887541770935},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.26112183928489685},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16800805926322937},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1410519778728485},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09249481558799744}],"concepts":[{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.8701549768447876},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8613893985748291},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.713835597038269},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6778420805931091},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.660330057144165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5384151339530945},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5303630828857422},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5127550363540649},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5040079951286316},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48957642912864685},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4861466586589813},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.4825098514556885},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.46457892656326294},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3470887541770935},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26112183928489685},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16800805926322937},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1410519778728485},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09249481558799744},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2004-275","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.454.5118","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.454.5118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mirlab.org/conference_papers/International_Conference/ICSLP 2004/contents/TuC_pdf/TuC2101p/TuC2101p.15_p830.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7200000286102295,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W51375597","https://openalex.org/W196142488","https://openalex.org/W1903355235","https://openalex.org/W2045656233","https://openalex.org/W2046079134","https://openalex.org/W2100969003","https://openalex.org/W2117621558","https://openalex.org/W2134501463","https://openalex.org/W2172085063"],"related_works":["https://openalex.org/W1595191759","https://openalex.org/W1503532423","https://openalex.org/W2010299594","https://openalex.org/W1967494390","https://openalex.org/W245717845","https://openalex.org/W3013496002","https://openalex.org/W2465363361","https://openalex.org/W2896820906","https://openalex.org/W2101542441","https://openalex.org/W4284711868"],"abstract_inverted_index":{"The":[0,19,37,98],"present":[1],"work":[2],"compares":[3],"three":[4,49],"different":[5],"methods":[6,50],"for":[7,92,108],"training":[8,117],"acoustic":[9],"models":[10,20],"in":[11],"a":[12,29,110],"Finnish":[13],"large":[14],"vocabulary":[15],"speech":[16],"recognition":[17,83],"system.":[18],"are":[21],"trained":[22],"using":[23,73,115],"the":[24,42,55,59],"maximum":[25,28],"likelihood":[26],"(ML),":[27],"posteriori":[30],"(MAP),":[31],"and":[32,75],"variational":[33],"Bayesian":[34],"(VB)":[35],"principle.":[36],"results":[38],"show":[39],"that":[40,103],"when":[41],"model":[43,56,93,113],"complexity":[44,57],"is":[45,71,102],"properly":[46],"chosen,":[47],"all":[48],"give":[51],"similar":[52],"performance.":[53],"As":[54],"increases,":[58],"perfor-mance":[60],"of":[61,100],"ML":[62],"based":[63,77],"system":[64],"starts":[65],"to":[66],"degrade":[67],"whereas":[68],"no":[69],"over-fitting":[70],"observed":[72],"MAP":[74,79],"VB":[76,86,101],"models.":[78],"gives":[80],"slightly":[81],"better":[82],"accuracy":[84],"over":[85],"but":[87],"it":[88,104],"cannot":[89],"be":[90,106],"used":[91,107],"selection":[94],"without":[95],"auxiliary":[96],"data.":[97,118],"advan-tage":[99],"can":[105],"selecting":[109],"well":[111],"performing":[112],"structure":[114],"only":[116],"1.":[119]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}